Diagnoses Kubernetes and OpenShift clusters in plain language, explaining why workloads are failing through a CLI, in-cluster operator, and MCP server.
Use it now
Keep it with up to 9 other tools you're setting up, then share them all as one link.
Try this first
Ask your assistant, with K8sGPT connected:
- Cluster Analyze
Use K8sGPT to scan a cluster for failing pods, services, and ingresses: ‹what you need›
- Custom Analyzer
Use K8sGPT to run targeted analysers against specific resource kinds: ‹what you need›
Connect it over MCP
Connect K8sGPT as an MCP server, following its setup instructions at https://github.com/k8sgpt-ai/k8sgpt
Its page: github.com/k8sgpt-ai/k8sgpt
Install the CLI
Install it as its own instructions say.
Its page: github.com/k8sgpt-ai/k8sgpt
Call the API
Auth An API key from K8sGPT
Its page: github.com/k8sgpt-ai/k8sgpt
Compare
Press Compare to add it to the tray at the bottom of the window, then pick up to 2 others anywhere on the site.
- Access
- CLIAPIMCP
- Auth
- API Key
- Skills
- 3
Skills
Cluster Analyze
Scans a cluster for failing pods, services, and ingresses and explains each root cause in plain language.
Custom Analyzer
Runs targeted analysers against specific resource kinds to narrow an ongoing investigation.
Operator Mode
Runs continuously in-cluster and publishes findings as custom resources for other tooling.
